Enable training model with a seeded PRNG

[mondus]

There is randomness involved in training the model (e.g. the DataLoader shuffling). Being able to control this may be useful.

This should be assertable by training twice on the same input data with the same seed: in theory, we should train two identical models with the identical weights.

---

(Original issue text)

This would aid some cases within the testing. Care must be taken for cases where stochasticity needs to be evaluated as part of testing.

[raehik]

A file testing the FCN model in Cem's fork includes the line torch.manual_seed(1). Seems reasonable.

https://github.com/CemGultekin1/gz21/blob/5c612e5dde6dcb03b07add09ccbfe54a6a6c4a32/gz21/adam_test.py#L5

[raehik]

#66 adds code to seed numpy and everything else that might touch a (P)RNG. It's not yet plugged into the rest of the code like Cem's fork is.

[raehik]

It's not clear how much randomness is actually involved. It may just be DataLoader shuffling...? Need a bit more PyTorch expertise, and understanding of any transformations that we perform.